mirror of
https://github.com/mudler/LocalAI.git
synced 2026-06-05 07:16:10 -04:00
* feat(distributed): NATS JWT auth, TLS/mTLS options, and e2e coverage Mint per-node NATS user JWTs at registration when LOCALAI_NATS_ACCOUNT_SEED is set, and connect workers with scoped credentials from the register response. Add optional LOCALAI_NATS_TLS_CA/CERT/KEY for private CA and mTLS alongside tls:// URLs, plus test-e2e-distributed and NatsJWT container e2e specs. Document JWT setup (nats-auth-setup.sh) and TLS env vars in distributed-mode. Assisted-by: Grok:grok grok-build Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(distributed): correct NATS JWT scoping and harden client auth The JWT-auth path added in 46467cc7 had several gaps that fail silently under LOCALAI_NATS_REQUIRE_AUTH: - Agent-worker minted JWTs did not allow the subjects the agent worker actually subscribes to (jobs.mcp-ci.new and nodes.<id>.backend.stop), so MCP-CI jobs and backend-stop session cleanup were silently dropped. Scope the agent permission set to those subjects. - NATS subscription permission violations were swallowed (Subscribe returned a live-but-dead subscription). Confirm subscriptions with a server round-trip so a denial surfaces synchronously, and log async permission errors. - The backend worker connected anonymously when given a JWT without its paired seed; reject the unpaired credential instead. - The documented service-user permissions in nats-auth-setup.sh omitted prefixcache.>, which the frontend publishes and subscribes; add it. Also: add a credential-provider hook to the messaging client (consumed by the follow-up credential-lifecycle change), drop the always-nil error from NatsMessagingOptions, run go mod tidy (jwt/v2 and nkeys are now direct), and gofmt the feature's files. Tests: an agent-JWT e2e spec that connects to the enforcing NATS server and exercises every subscription the agent worker makes, plus permission allow-list coverage unit tests. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com> * feat(distributed): acquire and auto-refresh worker NATS credentials Workers fetched NATS credentials once at startup, which broke two cases under JWT auth: a worker that registered while still pending admin approval never received a minted JWT (it connected unauthenticated and gave up), and a long-running worker's 24h JWT expired with no way to renew it. Introduce workerregistry.NATSCredentialManager, built on idempotent re-registration (the frontend preserves the node row and mints a fresh JWT each call): - Acquire re-registers through admin approval until the node is approved and credentials are minted (or returns the first success when auth is not required, preserving anonymous-NATS behavior). - RefreshLoop re-registers before the JWT expires (~75% of its lifetime), updating the credentials served to the connection. - Both are bounded (default 100 attempts / consecutive failures) and return an error on exhaustion, so an unapprovable or unrenewable worker exits non-zero and surfaces the problem instead of hanging or drifting toward an expired credential. The messaging client gains WithUserJWTProvider, fetching credentials on each (re)connect so the connection transparently adopts a refreshed JWT when the server expires the old one. RegisterFull exposes the approval status and full response; Register delegates to it. Both the backend worker and the agent worker are wired to this: explicit env credentials are used as-is, minted credentials are acquired-with-wait and refreshed, and a permanent refresh failure shuts the worker down so it restarts and re-acquires. Tests cover Acquire (wait-through-pending, bounded give-up, context cancel), RefreshLoop (refresh-before-expiry, bounded failure, no-expiry exit) and jwtExpiry decoding. Docs updated in distributed-mode.md. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com> --------- Signed-off-by: Richard Palethorpe <io@richiejp.com>
60 lines
1.6 KiB
Go
60 lines
1.6 KiB
Go
package natsauth
|
|
|
|
import (
|
|
"fmt"
|
|
"time"
|
|
|
|
"github.com/nats-io/jwt/v2"
|
|
"github.com/nats-io/nkeys"
|
|
)
|
|
|
|
// MintWorkerJWT creates a signed NATS user JWT and user seed scoped to nodeID and nodeType.
|
|
// The seed is returned once at registration so the worker can sign NATS connections.
|
|
func (c Config) MintWorkerJWT(nodeID, nodeType string) (userJWT, userSeed string, err error) {
|
|
if c.AccountSeed == "" {
|
|
return "", "", fmt.Errorf("natsauth: account seed not configured")
|
|
}
|
|
if nodeID == "" {
|
|
return "", "", fmt.Errorf("natsauth: node ID is required")
|
|
}
|
|
|
|
accountKP, err := nkeys.FromSeed([]byte(c.AccountSeed))
|
|
if err != nil {
|
|
return "", "", fmt.Errorf("natsauth: invalid account seed: %w", err)
|
|
}
|
|
|
|
userKP, err := nkeys.CreateUser()
|
|
if err != nil {
|
|
return "", "", fmt.Errorf("natsauth: create user key: %w", err)
|
|
}
|
|
seedBytes, err := userKP.Seed()
|
|
if err != nil {
|
|
return "", "", fmt.Errorf("natsauth: user seed: %w", err)
|
|
}
|
|
|
|
accountPub, err := accountKP.PublicKey()
|
|
if err != nil {
|
|
return "", "", fmt.Errorf("natsauth: account public key: %w", err)
|
|
}
|
|
userPub, err := userKP.PublicKey()
|
|
if err != nil {
|
|
return "", "", fmt.Errorf("natsauth: user public key: %w", err)
|
|
}
|
|
|
|
pubAllow, subAllow := WorkerPermissions(nodeID, nodeType)
|
|
|
|
uc := jwt.NewUserClaims(userPub)
|
|
uc.Name = fmt.Sprintf("localai-%s-%s", nodeType, workerSubjectToken(nodeID))
|
|
uc.IssuerAccount = accountPub
|
|
uc.Expires = time.Now().Add(c.WorkerTTL()).Unix()
|
|
|
|
uc.Permissions.Pub.Allow = pubAllow
|
|
uc.Permissions.Sub.Allow = subAllow
|
|
|
|
token, err := uc.Encode(accountKP)
|
|
if err != nil {
|
|
return "", "", fmt.Errorf("natsauth: encode user JWT: %w", err)
|
|
}
|
|
return token, string(seedBytes), nil
|
|
}
|